paper-with-me

Papers

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

2021-11-05 · Findings (EMNLP) 2021 11 · Yu Gai, Paras Jain, Wendi Zhang, Joseph E. Gonzalez, Dawn Song, Ion Stoica

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to more complex train-test splits. We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism. Grounding enables the model to retain syntax information from the input in thereby significantly improving generalization over complex inputs. By predicting a structured graph containing conjunctions of query clauses, we learn a group invariant representation without making assumptions on the target domain. Our model significantly outperforms state-of-the-art baselines on the Compositional Freebase Questions (CFQ) dataset, a challenging benchmark for compositional generalization in question answering. Moreover, we effectively solve the MCD1 split with 98% accuracy.

📄 PDF Abstract BibTeX arXiv:2111.03642

Code (1)

gaiyu0/cfq 공식 구현 pytorch

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding

2022-01-27 · Matthew Setzler, Scott Howland, Lauren Phillips

Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinations of known inputs, but less work has …

Decoder

Iterative Decoding for Compositional Generalization in Transformers

2021-10-08 · Luana Ruiz, Joshua Ainslie, Santiago Ontañón

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learnin…

Iterative Decoding for Compositional Generalization in Transformers

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learnin…

Compositional Generalization via Semantic Tagging

2020-10-22 · Findings (EMNLP) 2021 11 · Hao Zheng, Mirella Lapata

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen…

Semantic ParsingTAG

Compositional Generalization with Grounded Language Models

2024-06-07 · Sondre Wold, Étienne Simon, Lucas Georges Gabriel Charpentier, Egor V. Kostylev 외

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in s…

Knowledge GraphsSemantic Parsing